from __future__ import unicode_literals
-from .common import InfoExtractor
from .theplatform import ThePlatformFeedIE
from ..utils import (
ExtractorError,
xpath_element,
xpath_text,
update_url_query,
+ url_or_none,
)
})
return subtitles
+ def _extract_common_video_info(self, content_id, asset_types, mpx_acc, extra_info):
+ tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
+ tp_release_url = f'https://link.theplatform.com/s/{tp_path}'
+ info = self._extract_theplatform_metadata(tp_path, content_id)
+
+ formats, subtitles = [], {}
+ last_e = None
+ for asset_type, query in asset_types.items():
+ try:
+ tp_formats, tp_subtitles = self._extract_theplatform_smil(
+ update_url_query(tp_release_url, query), content_id,
+ 'Downloading %s SMIL data' % asset_type)
+ except ExtractorError as e:
+ last_e = e
+ if asset_type != 'fallback':
+ continue
+ query['formats'] = '' # blank query to check if expired
+ try:
+ tp_formats, tp_subtitles = self._extract_theplatform_smil(
+ update_url_query(tp_release_url, query), content_id,
+ 'Downloading %s SMIL data, trying again with another format' % asset_type)
+ except ExtractorError as e:
+ last_e = e
+ continue
+ formats.extend(tp_formats)
+ subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+ if last_e and not formats:
+ self.raise_no_formats(last_e, True, content_id)
+ self._sort_formats(formats)
+
+ extra_info.update({
+ 'id': content_id,
+ 'formats': formats,
+ 'subtitles': subtitles,
+ })
+ info.update({k: v for k, v in extra_info.items() if v is not None})
+ return info
+
+ def _extract_video_info(self, *args, **kwargs):
+ # Extract assets + metadata and call _extract_common_video_info
+ raise NotImplementedError('This method must be implemented by subclasses')
+
+ def _real_extract(self, url):
+ return self._extract_video_info(self._match_id(url))
+
class CBSIE(CBSBaseIE):
_VALID_URL = r'''(?x)
(?:
cbs:|
https?://(?:www\.)?(?:
- (?:cbs|paramountplus)\.com/(?:shows/[^/]+/video|movies/[^/]+)/|
+ cbs\.com/(?:shows/[^/]+/video|movies/[^/]+)/|
colbertlateshow\.com/(?:video|podcasts)/)
)(?P<id>[\w-]+)'''
+ # All tests are blocked outside US
_TESTS = [{
'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
'info_dict': {
# m3u8 download
'skip_download': True,
},
- '_skip': 'Blocked outside the US',
+ }, {
+ 'url': 'https://www.cbs.com/shows/the-late-show-with-stephen-colbert/video/60icOhMb9NcjbcWnF_gub9XXHdeBcNk2/the-late-show-6-23-21-christine-baranski-joy-oladokun-',
+ 'info_dict': {
+ 'id': '60icOhMb9NcjbcWnF_gub9XXHdeBcNk2',
+ 'title': 'The Late Show - 6/23/21 (Christine Baranski, Joy Oladokun)',
+ 'timestamp': 1624507140,
+ 'description': 'md5:e01af24e95c74d55e8775aef86117b95',
+ 'uploader': 'CBSI-NEW',
+ 'upload_date': '20210624',
+ },
+ 'params': {
+ 'ignore_no_formats_error': True,
+ 'skip_download': True,
+ },
+ 'expected_warnings': [
+ 'This content expired on', 'No video formats found', 'Requested format is not available'],
}, {
'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
'only_matching': True,
}, {
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True,
- }, {
- 'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
- 'only_matching': True,
- }, {
- 'url': 'https://www.paramountplus.com/movies/million-dollar-american-princesses-meghan-and-harry/C0LpgNwXYeB8txxycdWdR9TjxpJOsdCq',
- 'only_matching': True,
}]
def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
content_id, query={'partner': site, 'contentId': content_id})
video_data = xpath_element(items_data, './/item')
title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
- tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
- tp_release_url = 'https://link.theplatform.com/s/' + tp_path
- asset_types = []
- subtitles = {}
- formats = []
- last_e = None
+ asset_types = {}
for item in items_data.findall('.//item'):
asset_type = xpath_text(item, 'assetType')
- if not asset_type or asset_type in asset_types or 'HLS_FPS' in asset_type or 'DASH_CENC' in asset_type:
- continue
- asset_types.append(asset_type)
query = {
'mbr': 'true',
'assetTypes': asset_type,
}
- if asset_type.startswith('HLS') or asset_type in ('OnceURL', 'StreamPack'):
+ if not asset_type:
+ # fallback for content_ids that videoPlayerService doesn't return anything for
+ asset_type = 'fallback'
+ query['formats'] = 'M3U+none,MPEG4,M3U+appleHlsEncryption,MP3'
+ del query['assetTypes']
+ if asset_type in asset_types:
+ continue
+ elif any(excluded in asset_type for excluded in ('HLS_FPS', 'DASH_CENC', 'OnceURL')):
+ continue
+ if asset_type.startswith('HLS') or 'StreamPack' in asset_type:
query['formats'] = 'MPEG4,M3U'
elif asset_type in ('RTMP', 'WIFI', '3G'):
query['formats'] = 'MPEG4,FLV'
- try:
- tp_formats, tp_subtitles = self._extract_theplatform_smil(
- update_url_query(tp_release_url, query), content_id,
- 'Downloading %s SMIL data' % asset_type)
- except ExtractorError as e:
- last_e = e
- continue
- formats.extend(tp_formats)
- subtitles = self._merge_subtitles(subtitles, tp_subtitles)
- if last_e and not formats:
- raise last_e
- self._sort_formats(formats)
+ asset_types[asset_type] = query
- info = self._extract_theplatform_metadata(tp_path, content_id)
- info.update({
- 'id': content_id,
+ return self._extract_common_video_info(content_id, asset_types, mpx_acc, extra_info={
'title': title,
'series': xpath_text(video_data, 'seriesTitle'),
'season_number': int_or_none(xpath_text(video_data, 'seasonNumber')),
'episode_number': int_or_none(xpath_text(video_data, 'episodeNumber')),
'duration': int_or_none(xpath_text(video_data, 'videoLength'), 1000),
- 'thumbnail': xpath_text(video_data, 'previewImageURL'),
- 'formats': formats,
- 'subtitles': subtitles,
+ 'thumbnail': url_or_none(xpath_text(video_data, 'previewImageURL')),
})
- return info
-
- def _real_extract(self, url):
- content_id = self._match_id(url)
- return self._extract_video_info(content_id)
-
-
-class ParamountPlusSeriesIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?paramountplus\.com/shows/(?P<id>[a-zA-Z0-9-_]+)/?(?:[#?]|$)'
- _TESTS = [{
- 'url': 'https://www.paramountplus.com/shows/drake-josh',
- 'playlist_mincount': 50,
- 'info_dict': {
- 'id': 'drake-josh',
- }
- }, {
- 'url': 'https://www.paramountplus.com/shows/hawaii_five_0/',
- 'playlist_mincount': 240,
- 'info_dict': {
- 'id': 'hawaii_five_0',
- }
- }, {
- 'url': 'https://www.paramountplus.com/shows/spongebob-squarepants/',
- 'playlist_mincount': 248,
- 'info_dict': {
- 'id': 'spongebob-squarepants',
- }
- }]
- _API_URL = 'https://www.paramountplus.com/shows/{}/xhr/episodes/page/0/size/100000/xs/0/season/0/'
-
- def _entries(self, show_name):
- show_json = self._download_json(self._API_URL.format(show_name), video_id=show_name)
- if show_json.get('success'):
- for episode in show_json['result']['data']:
- yield self.url_result(
- 'https://www.paramountplus.com%s' % episode['url'],
- ie=CBSIE.ie_key(), video_id=episode['content_id'])
-
- def _real_extract(self, url):
- show_name = self._match_id(url)
- return self.playlist_result(self._entries(show_name), playlist_id=show_name)